Preprocessing of Non-symmetrical Images for Edge Detection

Abstract

One of the important parts of computer vision is segmenting an image into various uses. The key objective of any segmentation technique is to stop the segmentation at a point beyond which it is unnecessary. The images in which objects are surrounded by asymmetric background show all the edges of the background too, when traditional techniques of edge detection were used. Hence, it was difficult to recognize the actual components in the image. This paper is about the use of preprocessing techniques so that we can refine the result and obtain only the edges which are necessary excluding the background noise. The designing and testing of all the methods have been done on MATLAB software.